diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl
index 3ef69fa613..2ae9c8e5de 100644
--- a/.modelhub_state/recovery_intents.jsonl
+++ b/.modelhub_state/recovery_intents.jsonl
@@ -2702,7 +2702,7 @@
 {"batchId": "66398e18f2aa4aa6b83675255b3eb0a0", "completedAt": "2026-10-05T17:11:20.398975+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-05T17:11:19.012773+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f2f7a0fec18c41f2a579e6f135dfdbef", "lastModified": "2026-09-08T05:28:50+00:00", "modelAddress": "https://modelscope.cn/models/rapid-mlx/Qwen3.8-27B-4bit-MTP-fp16-MLX", "reason": null, "reconciledAt": "2026-10-06T07:57:23.767179+00:00", "repoId": "rapid-mlx/Qwen3.8-27B-4bit-MTP-fp16-MLX", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Biren_166m", "taskId": "5306227", "taskType": "text-generation"}
 {"batchId": "4eeadeb2b3a44f28a5dc31a0b805414f", "completedAt": "2026-10-05T18:17:07.212061+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-05T18:15:37.875183+00:00", "framework": "vllm_tokenizer_patch", "intentId": "970c221c6be2404d86b3654544d26173", "lastModified": "2026-10-05T18:02:26+00:00", "modelAddress": "https://modelscope.cn/models/unsloth/gpt-oss-20b-bnb-4bit", "reason": null, "reconciledAt": "2026-10-06T07:57:23.767978+00:00", "repoId": "unsloth/gpt-oss-20b-bnb-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Ascend_910-b3", "taskId": "5307270", "taskType": "text-generation"}
 {"batchId": "7a111132be1f40108640311f02a3ab3b", "completedAt": "2026-10-05T18:34:25.889573+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-05T18:34:23.644131+00:00", "framework": "vllm_fix_tokenizer", "intentId": "5d507ed6ed814f0d9761fd1fbadc0474", "lastModified": "2026-10-05T18:02:26+00:00", "modelAddress": "https://modelscope.cn/models/unsloth/gpt-oss-20b-bnb-4bit", "reason": null, "reconciledAt": "2026-10-06T07:57:23.767975+00:00", "repoId": "unsloth/gpt-oss-20b-bnb-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Biren_166m", "taskId": "5307498", "taskType": "text-generation"}
-{"batchId": "3564a7942281484b9c3164e2adf9119d", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-06T08:04:08.141766+00:00", "framework": "vllm_tokenizer_patch", "intentId": "97ea8d990dc44da9b135876d18f95e4f", "lastModified": "2026-09-21T18:33:19+00:00", "modelAddress": "https://modelscope.cn/models/GnLOLot/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic", "repoId": "GnLOLot/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
+{"batchId": "3564a7942281484b9c3164e2adf9119d", "completedAt": "2026-10-06T08:05:31.801641+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-06T08:04:08.141766+00:00", "framework": "vllm_tokenizer_patch", "intentId": "97ea8d990dc44da9b135876d18f95e4f", "lastModified": "2026-09-21T18:33:19+00:00", "modelAddress": "https://modelscope.cn/models/GnLOLot/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic", "reason": null, "repoId": "GnLOLot/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "MetaX_c-500", "taskId": "5319429", "taskType": "text-generation"}
 {"batchId": "9544bf0548e54a8e93c3adfd9bffb52a", "completedAt": "2026-10-03T16:15:51.005765+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-10-03T16:13:49.532883+00:00", "framework": "vllm-patch-tokenizer", "intentId": "7f7cb1b51f944ac58018ee2e42ca61f7", "repoId": "mlx-community/LFM2.5-1.2B-Instruct-6bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
 {"batchId": "6ad67bedd5104b958247ed686fa4a8d7", "completedAt": "2026-09-29T14:16:48.925444+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-09-29T14:16:45.683768+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ba30792e89b44ef5804d5f3613d7df71", "repoId": "nv-community/Qwen3.8-27B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "MetaX_c-500", "taskId": null, "taskType": "text-generation"}
 {"batchId": "6ad67bedd5104b958247ed686fa4a8d7", "completedAt": "2026-09-29T14:16:48.925408+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-09-29T14:16:45.683638+00:00", "framework": "vllm_tokenizer_patch", "intentId": "69aec4d25f21464c860135eb90d77735", "repoId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "MetaX_c-500", "taskId": null, "taskType": "text-generation"}
diff --git a/.modelhub_state/routing_intelligence.json b/.modelhub_state/routing_intelligence.json
index 3ce1912347..f007acbfeb 100644
--- a/.modelhub_state/routing_intelligence.json
+++ b/.modelhub_state/routing_intelligence.json
@@ -1,6 +1,6 @@
 {
   "acceptedByCategory": {
-    "unified_success_first": 2841
+    "unified_success_first": 2842
   },
   "acceptedByRoute": {
     "text-generation|Ascend_910-b3|llamacpp": 26,
@@ -29,7 +29,7 @@
     "text-generation|Kunlunxin_p-800|vllm_fix_tokenizer": 239,
     "text-generation|Kunlunxin_p-800|vllm_tokenizer_patch": 98,
     "text-generation|MetaX_c-500|vllm": 127,
-    "text-generation|MetaX_c-500|vllm_tokenizer_patch": 21,
+    "text-generation|MetaX_c-500|vllm_tokenizer_patch": 22,
     "text-generation|Mthreads_s4000|llamacpp": 21,
     "text-generation|Mthreads_s4000|vllm": 123,
     "text-generation|Sunrise_pt-200-x1|vllm": 87,
@@ -39,8 +39,8 @@
     "text-generation|hygon_k100-ai|vllm": 27,
     "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 153
   },
-  "acceptedSinceRefresh": 2841,
-  "acceptedTotal": 2841,
-  "generatedAt": "2026-10-05T18:34:25.850249+00:00",
+  "acceptedSinceRefresh": 2842,
+  "acceptedTotal": 2842,
+  "generatedAt": "2026-10-06T08:05:31.757718+00:00",
   "version": 1
 }
diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl
index 3f332ec562..9ab16ff760 100644
--- a/ledger/submissions.jsonl
+++ b/ledger/submissions.jsonl
@@ -936,3 +936,4 @@
 {"framework": "transformers", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-quantized.w8a16", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a16", "submitTime": "2026-09-21T18:32:49.780633+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5005549", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-transformers-iluvatar-bi-150"}
 {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/mlx-community/gpt-oss-20b-OptiQ-4bit", "modelId": "mlx-community/gpt-oss-20b-OptiQ-4bit", "submitTime": "2026-09-26T08:01:50.847636+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5097139", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
 {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/gpt-oss-20b-OptiQ-4bit", "modelId": "mlx-community/gpt-oss-20b-OptiQ-4bit", "submitTime": "2026-09-26T08:18:32.495861+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5097281", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
+{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/GnLOLot/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic", "modelId": "GnLOLot/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic", "submitTime": "2026-10-06T08:05:30.743848+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319429", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-metax-c-500"}
diff --git a/manifest.json b/manifest.json
index f6b25adc14..e01c0b931f 100644
--- a/manifest.json
+++ b/manifest.json
@@ -10,16 +10,16 @@
     ".modelhub_state/queue_cleanup_latest.json": "bfbda40c7dc7bfebce797c1bb61357de5e74b019bdbb08e50f8f19323e95a84c",
     ".modelhub_state/recent_outcomes.jsonl": "66f65405defcf850f044e43e54c3dc291f18521f309cb9962d861b493cb049ac",
     ".modelhub_state/recovery_active_tasks.jsonl": "c5a398a519517b4a0e21970ecf20dd5396282eb9b2cce4fc20519dcc500bb1e2",
-    ".modelhub_state/recovery_intents.jsonl": "dff30eabd2fc5f9d8bf3610df23aaf41830e427190853b4d5cbb050b16206a57",
-    ".modelhub_state/routing_intelligence.json": "fd679e61008e930cca88ce220ce5fcded760a926d2391985ac149cdba5cdec55",
+    ".modelhub_state/recovery_intents.jsonl": "41939b0393943bda24e46e6bb26bb8470b15214ffb1c45e592292c8b55084d25",
+    ".modelhub_state/routing_intelligence.json": "5ab1ea8ddd87c9d04651c4c4446fa735b1a558ee1c17d239b2bcf5c00cf5da38",
     ".modelhub_state/submission_exclusions.jsonl": "8a533753b09639322718ffe59fad6a6f11e8cc3741d7be12085a149c97ca5507",
     ".modelhub_state/worker_crashes.jsonl": "b321ea3648ae6b322601ed30ef8c3b1da0f13612af1bde3a64b0d41dc18a7b9f",
-    "ledger/submissions.jsonl": "e8c245ce0faa91b38b94ce83ad985417d9a475bd81e46b227a3cdf620dd72182",
-    "outcomes/submissions.jsonl": "16ad14643e48c98e9fb31d1f08858224b3722056cb158f480688ab6a94fc7c52"
+    "ledger/submissions.jsonl": "383bd20dcba00ba540c370675e2e2776d16ae311636a627193751c117d2fd8df",
+    "outcomes/submissions.jsonl": "e23c8bc6c4fdd6e3252062b0800956d315341c66084c4653704cb7b8760a9829"
   },
-  "generation": 21343,
-  "phase": "intent",
+  "generation": 21344,
+  "phase": "result",
   "schemaVersion": 1,
-  "updatedAt": "2026-10-06T08:04:08.268307+00:00",
+  "updatedAt": "2026-10-06T08:05:31.902899+00:00",
   "writerId": "c99196ebc91b43dbbcacb4830cce7e56"
 }
diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl
index c4ea85a009..78377e4bd9 100644
--- a/outcomes/submissions.jsonl
+++ b/outcomes/submissions.jsonl
@@ -722,3 +722,4 @@
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T01:13:33.049671+00:00", "modelId": "rapid-mlx/Qwen3.8-27B-4bit-MTP-fp16-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16293474195, "estimatedRequiredGiB": 18.239, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 16320426072, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4665462000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:rapid-mlx", "custom_tag:qwen3.8", "custom_tag:qwen3.8-27b", "custom_tag:4-bit", "custom_tag:fp16", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 16320426072, "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 3}, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T16:15:27.384896+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3}, "recursiveRepositoryBytes": 16320426072, "repositoryOnDiskBytes": 16320426072}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-05T17:11:20.150043+00:00", "targetGpu": "Biren_166m", "taskId": "5306227", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T02:18:00.653125+00:00", "modelId": "unsloth/gpt-oss-20b-bnb-4bit", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 40884615394, "estimatedRequiredGiB": 45.723, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 40912596558, "modelscopeLicense": "apache-2.0", "modelscopeParams": 20934761652, "modelscopeTags": ["license:apache-2.0", "model_type:gpt_oss", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:openai", "custom_tag:unsloth"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 40912596558, "quantizationMethod": "bitsandbytes", "recursiveRepositoryBytes": 40912599808, "repositoryOnDiskBytes": 40912599808}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-05T18:17:07.068675+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5307270", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T02:40:20.542511+00:00", "modelId": "unsloth/gpt-oss-20b-bnb-4bit", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 40884615394, "estimatedRequiredGiB": 45.723, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 40912596558, "modelscopeLicense": "apache-2.0", "modelscopeParams": 20934761652, "modelscopeTags": ["license:apache-2.0", "model_type:gpt_oss", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:openai", "custom_tag:unsloth"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 40912596558, "quantizationMethod": "bitsandbytes", "recursiveRepositoryBytes": 40912599808, "repositoryOnDiskBytes": 40912599808}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-05T18:34:25.654316+00:00", "targetGpu": "Biren_166m", "taskId": "5307498", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "GnLOLot/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.638, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:thinking", "custom_tag:fable5", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:agentic", "custom_tag:coding", "custom_tag:instruction-following", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": null, "quantizationMethod": null, "recursiveRepositoryBytes": 5045067151, "repositoryOnDiskBytes": 5045067151}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T08:05:30.743848+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319429", "taskType": "text-generation", "verifyResult": null}